import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import warnings

warnings.simplefilter(action='ignore', category=FutureWarning)

df = pd.read_csv('tweets.csv', index_col=0)
df

df.drop(['Datetime', 'Tweet Id', 'Username', 'sentiment_score', 'emotion', 'emotion_score'], axis=1, inplace=True)
df.rename(columns={'Text': 'text', 'sentiment': 'label'}, inplace=True)

# renaming classes
labels = {
    'negative': 0,
    'neutral': 1,
    'positive': 2,
}

df['label'] = df['label'].apply(lambda x: labels[x])
df

df.isna().sum()

df.duplicated().sum()

from copy import deepcopy

sns.set(style="whitegrid")
NAVY_LIGHT = '#4B527E'
NAVY_DARK = '#7C81AD'

# For better plot visualisation I saved duplicates  in second data frame
df_duplicates = deepcopy(df)
df.drop_duplicates(subset='text', keep='first', inplace=True)

fig = plt.figure()
fig = sns.countplot(df_duplicates, x='label', color='red', linewidth=0)
fig = sns.countplot(df, x='label', color=NAVY_DARK, linewidth=0)

plt.tight_layout()
plt.title('Duplicates per label')
plt.legend(['duplicates', 'unique'])

df.duplicated('text').sum()

df.value_counts('label')

from sklearn.utils import resample

df_by_label = lambda i: df[df['label'] == i]
downsampled_df = pd.DataFrame(data=df_by_label(1))
max_size = len(df_by_label(1))

# resampling classes
for i in [0, 2]:
    downsampled_class = resample(df_by_label(i),
                                 replace=True,
                                 n_samples=max_size,
                                 random_state=42)
    downsampled_df = pd.concat([downsampled_df, downsampled_class])

fig = plt.figure()

fig = sns.countplot(df, x='label', color=NAVY_LIGHT)

fig = sns.countplot(downsampled_df, x='label', color=NAVY_DARK, linewidth=0)
fig.axhline(y=max_size, color='r', linestyle=':')
fig.set_title('Balancing classes')

plt.tight_layout()
plt.show()

from matplotlib.lines import Line2D
from scipy.stats import hmean

# creating 3rd column that contains length in words of corresponding text data
df['length'] = df['text'].apply(lambda x: len(x.split()))
downsampled_df['length'] = downsampled_df['text'].apply(lambda x: len(x.split()))
df_by_label = lambda x: df[df['label'] == x]

fig, axes = plt.subplots(nrows=2, ncols=1, figsize=(20, 10))
sns.countplot(df, x='length', ax=axes[0])

colors = ['red', 'grey', 'green']
for i, color in enumerate(colors):
    count_by_length = df_by_label(i)['length'].value_counts().sort_index()
    sns.lineplot(x=count_by_length.index, y=count_by_length.values, marker=None, color=color, linewidth=3, ax=axes[1])

axes[0].set_title('Whole dataset')
axes[0].set_ylabel('Count')
axes[0].set_xlabel('Length (in words)')
axes[0].set_xlim(-1, 65)

axes[1].set_title('By class')
axes[1].set_ylabel('Count')
axes[1].set_xlabel('Length (in words)')
axes[1].set_xlim(1, 70)

legend_labels = ['negative', 'neutral', 'positive']
custom_lines = [Line2D([0], [0], color=colors[i], lw=3) for i in range(len(colors))]
axes[1].legend(custom_lines, legend_labels)

print(f"{'Mean':>20}: {int(df['length'].mean())}\n"
      f"{'Harmonic mean':>20}: {int(hmean(df['length']))}")

fig.suptitle('Amount of sentences per length', fontsize=20)
plt.tight_layout()
plt.show()

# cutting off the sentences, technically we don't need the length column for this
df_cut = df[(df['length'] >= 3) & (df['length'] <= 55)]
downsampled_df = downsampled_df[(downsampled_df['length'] >= 3) & (downsampled_df['length'] <= 55)]

min_count = len(df[df['length'] == 100])

fig, axes = plt.subplots(nrows=1, ncols=1, figsize=(30, 5))
sns.countplot(df, x='length', color=NAVY_LIGHT)
sns.countplot(df_cut, x='length', color=NAVY_DARK)

plt.axhline(y=100, color='red', linestyle=':')

print(f"{"Mean":>20}: {int(df['length'].mean())}\n"
      f"{"Harmonic mean":>20}: {int(hmean(df['length']))}")

fig.suptitle('Amount of sentences per length', fontsize=20)
axes.set_xlabel('Length (in words)')
plt.show()

df = df_cut

weights = dict()
for i in range(3):
    weights[i] = len(df) / len(df[df['label'] == i]) * 6
weights

from sklearn.feature_extraction.text import BaseEstimator, TransformerMixin, TfidfVectorizer
from nltk.stem import SnowballStemmer, WordNetLemmatizer
from nltk.corpus import stopwords
from string import punctuation
import emoji

class TextTokenizer(BaseEstimator, TransformerMixin):
    def __init__(self, emoji=True, mentions=True):
        self.stemmer = SnowballStemmer('english')
        self.emoji = emoji
        self.mentions = mentions
    
    def fit(self, X, y=None):
        return self
    
    def transform(self, X):
        processed_text = []
        
        for text in X:
            if self.emoji:
                text = emoji.demojize(text, delimiters=("", " "))
                text = text.replace("_", " ")
            if self.mentions:
                text = ' '.join(word for word in text.split() if word[0] != '@')
            text = ''.join(char.lower() for char in text if char not in punctuation)
            tokens = ' '.join(self.stemmer.stem(word) for word in text.split())
            processed_text.append(tokens)
            
        return processed_text

a = "😊😡   i don't care! #happy"
b = "smiling face emoji"
c = '@user23 thats #cRaZy!'

tokenizer = TextTokenizer()
for sentence in [a, b, c]:
    print(f"before: {sentence}\n after: {tokenizer.transform([sentence])}")
    print('')

from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.linear_model import SGDClassifier
from sklearn.feature_extraction.text import CountVectorizer

# TRAIN TEST SPLIT FOR DEFAULT DATA
x = df.iloc[:, 0]
y = df.iloc[:, 1]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)

# TRAIN TEST SPLIT FOR DOWNSAMPLED DATA
x_2 = downsampled_df.iloc[:, 0]
y_2 = downsampled_df.iloc[:, 1]
x_train_2, x_test_2, y_train_2, y_test_2 = train_test_split(x_2, y_2, test_size=0.2, random_state=42)

sgd_ds_2 = Pipeline([
    ('tok', TextTokenizer()),
    ('vec', CountVectorizer(ngram_range=(1, 2), stop_words=stopwords.words('english'))),
    ('clf', SGDClassifier(random_state=42, n_jobs=-1, shuffle=True))])

# default - unbalanced data, no custom transformer
sgd = deepcopy(sgd_ds_2)
sgd.set_params(clf__class_weight=weights)
sgd.steps.remove(sgd.steps[0])

# default - unbalanced data + custom transformer
sgd_2 = deepcopy(sgd_ds_2)
sgd_2.set_params(clf__class_weight=weights)

# downsampled, no custom transformer
sgd_ds = deepcopy(sgd_ds_2)
sgd_ds.steps.remove(sgd_ds.steps[0])

sgd, sgd_2, sgd_ds, sgd_ds_2

sgd.fit(x_train, y_train)
pred_default = sgd.predict(x_test)

sgd_2.fit(x_train, y_train)
pred_default_2 = sgd.predict(x_test)

sgd_ds.fit(x_train_2, y_train_2)
pred_ds = sgd_ds.predict(x_test_2)

sgd_ds_2.fit(x_train_2, y_train_2)
pred_ds_2 = sgd_ds_2.predict(x_test_2)

from sklearn.metrics import confusion_matrix, classification_report, f1_score

fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(10, 10))

mat_default = confusion_matrix(y_test, pred_default)
mat_default_2 = confusion_matrix(y_test, pred_default_2)
mat_downsampled = confusion_matrix(y_test_2, pred_ds)
mat_downsampled_2 = confusion_matrix(y_test_2, pred_ds_2)

for i, mat in enumerate([mat_default, mat_default_2, mat_downsampled, mat_downsampled_2]):
    sns.heatmap(mat.T, annot=True, fmt='d', square=True, cbar=False, cmap='Blues', ax=axes.flatten()[i])
    
axes.flatten()[0].set_title('Unbalanced data,weighted')
axes.flatten()[1].set_title('Unbalanced data, weighted, custom tokenizer')
axes.flatten()[2].set_title('Downsampled data')
axes.flatten()[3].set_title('Downsampled data, custom tokenizer')

for i in range(4):
    axes.flatten()[i].set_xlabel('true label')
    axes.flatten()[i].set_ylabel('predicted label')

print(f"Unbalanced data,weighted:\n{classification_report(y_test, pred_default)}\n\n")
print(f"Unbalanced data, weighted, custom tokenizer:\n{classification_report(y_test, pred_default_2)}\n\n")
print(f"Downsampled data:\n{classification_report(y_test_2, pred_ds)}\n\n")
print(f"Downsampled data, custom tokenizer:\n{classification_report(y_test_2, pred_ds_2)}")

plt.tight_layout()
plt.show()

from sklearn.model_selection import GridSearchCV

parameters = {
    'tok__emoji': [True, False],
    'tok__mentions': [True, False],
    # 'vec__ngram_range': [(1,1), (1,2), (2,3)],
    # 'clf__loss': ['hinge', 'log_loss', 'modified_huber', 'perceptron', 'huber', 'epsilon_insensitive'],
    # 'clf__penalty': ['elasticnet', 'l1', 'l2', None],
    # 'clf__learning_rate': ['constant', 'optimal', 'adaptive', 'invscaling'],
    # 'clf__shuffle': [True, False],
    # 'clf__alpha': np.linspace(0, 10, 5),
    # 'clf__epsilon': np.linspace(0, 10, 5),
    # 'clf__eta0': np.linspace(0, 1, 5),
}

gs_clf = GridSearchCV(sgd_ds_2, parameters, n_jobs=-1, verbose=1)
gs_clf = gs_clf.fit(x_train_2, y_train_2)

print(gs_clf.best_score_)
print(gs_clf.best_params_)

sgd_ds_2 = Pipeline([
    ('tok', TextTokenizer()),
    ('vec', CountVectorizer(ngram_range=(1, 2), stop_words=stopwords.words('english'))),
    ('clf', SGDClassifier(random_state=42, n_jobs=-1, penalty='elasticnet', shuffle=True,
                          loss='log_loss', learning_rate='adaptive', eta0=0.11, alpha=7e-05, epsilon=0.8)),
])

# default - unbalanced data, no custom transformer
sgd = deepcopy(sgd_ds_2)
sgd.set_params(clf__class_weight=weights)
sgd.steps.remove(sgd.steps[0])

# default - unbalanced data + custom transformer
sgd_2 = deepcopy(sgd_ds_2)
sgd_2.set_params(clf__class_weight=weights)

# downsampled, no custom transformer
sgd_ds = deepcopy(sgd_ds_2)
sgd_ds.steps.remove(sgd_ds.steps[0])

sgd.fit(x_train, y_train)
pred_default = sgd.predict(x_test)

sgd_2.fit(x_train, y_train)
pred_default_2 = sgd.predict(x_test)

sgd_ds.fit(x_train_2, y_train_2)
pred_ds = sgd_ds.predict(x_test_2)

sgd_ds_2.fit(x_train_2, y_train_2)
pred_ds_2 = sgd_ds_2.predict(x_test_2)

from sklearn.metrics import confusion_matrix, classification_report, f1_score

fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(10, 10))

mat_default = confusion_matrix(y_test, pred_default)
mat_default_2 = confusion_matrix(y_test, pred_default_2)
mat_downsampled = confusion_matrix(y_test_2, pred_ds)
mat_downsampled_2 = confusion_matrix(y_test_2, pred_ds_2)

for i, mat in enumerate([mat_default, mat_default_2, mat_downsampled, mat_downsampled_2]):
    sns.heatmap(mat.T, annot=True, fmt='d', square=True, cbar=False, cmap='Blues', ax=axes.flatten()[i])

axes.flatten()[0].set_title('Unbalanced data,weighted')
axes.flatten()[1].set_title('Unbalanced data, weighted, custom tokenizer')
axes.flatten()[2].set_title('Downsampled data')
axes.flatten()[3].set_title('Downsampled data, custom tokenizer')

for i in range(4):
    axes.flatten()[i].set_xlabel('true label')
    axes.flatten()[i].set_ylabel('predicted label')

print(f"Unbalanced data,weighted:\n{classification_report(y_test, pred_default)}\n\n")
print(f"Unbalanced data, weighted, custom tokenizer:\n{classification_report(y_test, pred_default_2)}\n\n")
print(f"Downsampled data:\n{classification_report(y_test_2, pred_ds)}\n\n")
print(f"Downsampled data, custom tokenizer:\n{classification_report(y_test_2, pred_ds_2)}")

plt.tight_layout()
plt.show()

negative_sentences = [
    # ~5 Words
    "I hate this so much. 😡",
    "Worst experience ever. 👎 #disappointed",
    "This is so frustrating. 😠",
    "Totally not worth it. 💸",
    "@user213 You ruined everything. 😤",
    "I can’t stand this. 😒",
    "This is pure garbage. 🚮",
    "Unbelievably bad service. 😤 #neveragain",
    "What a waste of time. 🕒",
    "Seriously the worst ever. ❌",

    # ~10 Words
    "I can't believe how awful this turned out to be. 😡 #fail",
    "@user213 You really let me down, very disappointed in you.",
    "This is the worst product I’ve ever purchased. Refund, please! 💸",
    "Completely ruined my day, thanks for nothing. 😠 #neveragain",
    "Everything about this is just terrible, never using it again. ❌",
    "@user213 Your customer support is useless and unhelpful, so frustrating! 😤",
    "Honestly, I expected much better from you, this is trash. 🚮",
    "Can’t believe I wasted money on this, so regretful. 💸",
    "I am so upset right now, what a huge letdown. 😡",
    "Honestly, this entire experience has been nothing but a headache. 😠"
]

neutral_sentences = [
    # ~5 Words
    "It was okay, nothing special. 🤷‍♂️",
    "Not good, not bad either.",
    "Just an average experience today.",
    "Meh, it’s alright I guess. 😐",
    "@user213 Could be better, honestly.",
    "This is neither here nor there.",
    "Just a regular day. 🤔",
    "I feel indifferent about it.",
    "Nothing to complain about. 🤷‍♀️",
    "It's fine, I suppose. 😶",

    # ~10 Words
    "I guess it’s just fine, nothing really stood out. 🤷‍♂️",
    "Not amazing, but not terrible either, just kind of average.",
    "@user213 It’s okay, not sure how I feel about it.",
    "This was pretty much what I expected, nothing surprising here.",
    "Honestly, I’m neither impressed nor disappointed, just neutral. 😐",
    "I don’t really have a strong opinion on this one.",
    "It’s fine, nothing to rave about or criticize. 🤷‍♀️",
    "Neither satisfied nor dissatisfied, just another average experience. 🤔",
    "@user213 It was pretty standard, nothing particularly great or bad.",
    "I’d call it a very average experience, to be honest. 😶"
]

positive_sentences = [
    # ~5 Words
    "Absolutely loved it! 😍 #amazing",
    "This made my day! 😊",
    "Fantastic job, @user213! 🌟",
    "I’m so happy! 🥳 #blessed",
    "Worth every penny! 💰",
    "Super excited about this! 😃",
    "Best decision ever made. 🙌",
    "Love this so much! 💖",
    "So proud of you, @user213!",
    "Can’t stop smiling! 😊",

    # ~10 Words
    "I’m incredibly happy with this, exceeded all my expectations! 😍",
    "Thank you, @user213, for such a fantastic experience! 🌟 #grateful",
    "This product has genuinely improved my life, super grateful! 💖",
    "I am over the moon with how this turned out. 😊",
    "Wow, just wow! Couldn’t have asked for anything better. 🙌",
    "Amazing experience from start to finish, highly recommend! 🌟 #bestdayever",
    "I’m so glad I tried this, totally worth it. 😊",
    "You nailed it, @user213! I’m really impressed! 👏",
    "I couldn’t be happier with the results, totally satisfied. 😃",
    "This exceeded my expectations, truly a delightful surprise! 🌟"
]

score_df = {
    'Model': ['positive', 'neutral', 'negative', 'average'],
    'Default': [0, 0, 0, 0],
    'Default + Custom tokenizer': [0, 0, 0, 0],
    'Downsampled': [0, 0, 0, 0],
    'Downsampled + Custom tokenizer': [0, 0, 0, 0]
}

score_df = pd.DataFrame(score_df).set_index('Model')

for i_2, model in enumerate([sgd, sgd_2, sgd_ds, sgd_ds_2]):
    avg_score = 0
    for i_1, sentiment in enumerate([negative_sentences, neutral_sentences, positive_sentences]):
        predictions = model.predict(sentiment)
        score = (np.array(predictions == i_1).sum() / 20) * 100
        score_df.iloc[i_1, i_2] = score
        avg_score += score

    avg_score =  round(avg_score / 3, 1)
    score_df.iloc[3, i_2] = avg_score

score_df

fig = plt.figure(figsize=(10, 6))
fig = sns.barplot(data=score_df.iloc[3], palette=sns.color_palette('Blues', 4))
fig.set_title('Score vs Model', fontweight='bold')
fig.set_ylim(0, 100)
plt.show()